Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Eugene Ng Yi Sheng, Bingquan Shen
• Venue: arXiv: cs.AI
• Published: 2026-07-09
• Collected: 2026-07-10
• URL: http://arxiv.org/abs/2607.08652v1
• PDF: https://arxiv.org/pdf/2607.08652v1
• DOI: UNKNOWN

Plain-Language Brief

The research presented investigates mechanisms that allow societies of self-interested agents to maintain market stability, focusing on a multi-agent marketplace simulation with 18 AI agents. The study identifies Mediation as the top-performing mechanism, which allows for market recovery even under adversarial attacks. The authors define 'adversarial robustness' as a mechanism's ability to sustain positive utility for honest agents under optimized attacks and find that Mediation is indeed robust.

What the Document Says

• The study focuses on maintaining market stability in societies of self-interested agents.
• A multi-agent marketplace simulation with 18 AI agents was used for the research.
• The top-performing mechanism identified is Mediation.
• Mediation allows for market recovery even under adversarial attacks.
• The authors define 'adversarial robustness' as a mechanism's ability to sustain positive utility for honest agents under optimized attacks.
• Mediation is found to be robust.

Key Concepts Mentioned

• self-interested agents
• market stability
• multi-agent marketplace simulation
• LLM agents (DeepSeek-V3)
• adversarial attack
• Mediation
• adversarial robustness

Claims Made by the Document

• Unconstrained self-interested agents tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse.
• The top-performing mechanism identified (Mediation) allows for market recovery even under adversarial attacks.
• Mediation is robust.

Evidence Used

• The paper describes the research question and the multi-agent marketplace simulation as a method.
• Results from the two experimental phases (mechanism comparison and adversarial red-teaming) support the claims about Mediation's performance.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such agents to maintain market stability, and how resilient those mechanisms are to adversarial attack. We instantiate the research question as a multi-agent marketplace simulation where 18 LLM agents (DeepSeek-V3) with complementary production specialties must trade within a constrained social network to obtain utility. We conduct two experimental phases: (1) a mechanism comparison across eight conditions under progressive troll injection over 200 rounds, identifying Mediation as the top-performing mechanism; and (2) adversarial red-teaming of Mediation using iteratively prompt-optimised LLM-driven trolls, finding that the best attack (v6) reduces honest-agent utility by 13.3% but cannot collapse the market. Mediation enables recovery even under sustained adversarial pressure. We define adversarial robustness as a mechanism's ability to sustain positive honest-agent utility under optimised attack, and find that Mediation is robust: it can be bent but not broken.